Embodiments provide systems, methods, and computer-readable storage media configured to leverage blockchain technologies to provide failsafe action and fault mitigation processing for autonomous systems. Such autonomous systems may include self-driving cars, logistics or manufacturing robots, or control processes in chemical manufacturing and processing facilities, or construction machinery or sites, and may utilize artificial intelligence (AI) and/or machine learning (ML) algorithms to control operations. These algorithms may be imperfect and subject to error. The disclosed blockchain-based techniques perform data analysis in a parallel and distributed manner (e.g., locally at the autonomous system and remotely at a node of a blockchain platform) to validate the information provided to the AI and/or ML algorithms, as well as the outputs of the algorithms. When anomalies or other issues are detected based on the data analysis, one or more failsafe actions may be executed to control operation of the autonomous systems in a safe manner.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
2. The method of claim 1, wherein the autonomous system is an autonomous vehicle, an autonomous robot, machinery, an autonomous plant, or construction site.
This invention relates to autonomous systems, including autonomous vehicles, robots, machinery, plants, and construction sites, addressing the challenge of optimizing their operation through adaptive control. The method involves dynamically adjusting the system's behavior based on real-time data and environmental conditions to improve efficiency, safety, or performance. The autonomous system is equipped with sensors and processing capabilities to gather and analyze data, enabling it to make decisions without human intervention. For example, an autonomous vehicle may adjust its speed or route based on traffic conditions, while an autonomous robot may modify its task sequence to avoid obstacles. The system may also incorporate machine learning to refine its decision-making over time. The invention ensures that the autonomous system operates reliably and efficiently in varying environments, reducing the need for manual oversight. This approach is particularly useful in industries where automation is critical, such as manufacturing, logistics, and infrastructure management. The method enhances the adaptability and responsiveness of autonomous systems, making them more versatile and effective in real-world applications.
3. The method of claim 1, further comprising writing at least a portion of the dataset to a block of a blockchain.
A system and method for data management involves processing a dataset to generate a cryptographic hash of the dataset. The cryptographic hash is then used to verify the integrity and authenticity of the dataset. The method further includes writing at least a portion of the dataset to a block of a blockchain. The blockchain serves as a decentralized, tamper-evident ledger, ensuring that the data cannot be altered without detection. This approach enhances data security by providing a verifiable record of the dataset's state at a specific point in time. The blockchain entry may include metadata such as timestamps, user identifiers, or other relevant information to further validate the data's origin and integrity. This method is particularly useful in applications requiring high levels of trust, such as financial transactions, supply chain tracking, or digital identity verification. By leveraging blockchain technology, the system ensures that the dataset remains immutable and transparent, reducing the risk of fraud or unauthorized modifications. The cryptographic hash provides an additional layer of security, allowing for efficient verification of the dataset's authenticity.
4. The method of claim 1, wherein the first data comprises sensor data generated by one or more sensors of the autonomous system.
This invention relates to autonomous systems, specifically methods for processing and utilizing sensor data to improve system performance. The technology addresses the challenge of efficiently collecting, analyzing, and applying sensor data in real-time to enhance decision-making and operational accuracy in autonomous systems. The method involves generating sensor data from one or more sensors integrated into the autonomous system. These sensors may include cameras, LiDAR, radar, ultrasonic sensors, or other environmental detection devices. The sensor data is collected to monitor the system's surroundings, detect obstacles, track movement, or gather other relevant environmental information. The data is then processed to extract meaningful insights, such as object detection, localization, or environmental mapping, which are used to guide the autonomous system's actions. This processing may involve filtering, calibration, fusion of multiple sensor inputs, or machine learning-based analysis to improve accuracy and reliability. By incorporating sensor data into the autonomous system's decision-making process, the method enables more precise navigation, obstacle avoidance, and adaptive responses to dynamic environments. The system can adjust its behavior in real-time based on the processed sensor inputs, ensuring safer and more efficient operation. This approach is particularly useful in applications such as autonomous vehicles, drones, robotics, and other autonomous platforms where environmental awareness is critical.
5. The method of claim 1, further comprising configuring information for processing by the artificial intelligence or machine learning algorithm, wherein the first data comprises the information configured for processing by the artificial intelligence or machine learning algorithm.
This invention relates to artificial intelligence (AI) and machine learning (ML) systems, specifically addressing the challenge of efficiently processing and configuring data for AI/ML algorithms. The method involves preparing data for analysis by AI/ML models, ensuring the data is structured and formatted in a way that enhances algorithmic performance. The system collects first data, which includes information specifically configured for AI/ML processing, such as labeled datasets, feature vectors, or preprocessed inputs. This data is then processed by an AI/ML algorithm to generate outputs, such as predictions, classifications, or insights. The configuration step ensures the data meets the requirements of the algorithm, improving accuracy and efficiency. The method may also involve preprocessing steps like normalization, feature extraction, or data augmentation to optimize the input for the AI/ML model. By structuring the data in this way, the system enhances the model's ability to learn patterns and make accurate decisions. The invention is particularly useful in applications like predictive analytics, natural language processing, and automated decision-making systems.
6. The method of claim 1, wherein the dataset comprises network data, and wherein the analyzing comprises detecting at least network congestion, network attacks, or both based on the network data.
This invention relates to network monitoring and security, specifically to methods for analyzing network data to detect issues such as congestion or attacks. The method involves processing a dataset containing network data, which may include traffic patterns, packet information, or other network-related metrics. The analysis step identifies anomalies or deviations that indicate network congestion, such as bandwidth saturation or latency spikes, or network attacks, such as intrusion attempts, malware propagation, or denial-of-service events. The detection process may use statistical analysis, machine learning, or rule-based systems to evaluate the network data against known threat signatures or performance thresholds. By continuously monitoring and analyzing the network data, the system can provide real-time alerts or automated responses to mitigate detected issues. The method improves network reliability and security by proactively identifying and addressing potential disruptions or malicious activity.
7. The method of claim 1, wherein the dataset comprises location data, and wherein the analyzing comprises detecting inconsistencies with respect to distances to one or more obstacles proximate the autonomous system based on the location data and the second data.
The invention relates to autonomous systems, specifically methods for analyzing datasets to improve operational safety and accuracy. The method involves processing a dataset containing location data from an autonomous system, such as a vehicle or robot, and comparing it with additional data to detect inconsistencies. The analysis focuses on identifying discrepancies in distance measurements to nearby obstacles, ensuring the autonomous system accurately perceives its environment. By cross-referencing the location data with the second dataset, the method can flag potential errors in obstacle detection, such as miscalculated distances or false obstacle identifications. This helps prevent collisions and improves navigation reliability. The method may also involve adjusting the autonomous system's behavior based on the detected inconsistencies, such as recalculating a path or triggering a safety protocol. The approach enhances situational awareness by validating sensor inputs against reference data, reducing reliance on potentially faulty measurements. This is particularly useful in dynamic environments where obstacle positions may change rapidly, ensuring the autonomous system operates safely and efficiently.
8. The method of claim 1, wherein the control data comprises instructions to execute a failsafe action, the failsafe action comprising an action selected from the list consisting of: slowing a speed of the autonomous system, increasing a speed of the autonomous system, changing a direction of travel of the autonomous system, stopping the autonomous system, removal of fuel supply, removal of electricity supply, triggering of collision protection devices such as airbags and sirens, turning off of fuel supply/pumps, turning off of reagent supply/pumps, shutting down a drilling subsystem, shutting down one or more chemical reactors, triggering of fire alarms, and triggering of sprinklers.
This invention relates to autonomous systems and methods for controlling them, particularly in response to detected anomalies or failures. The technology addresses the challenge of ensuring safety and operational integrity in autonomous systems when unexpected conditions arise. The method involves generating control data that includes instructions to execute a failsafe action. These failsafe actions are designed to mitigate risks and prevent harm by altering the system's behavior or state. The actions include slowing or increasing the system's speed, changing its direction, or stopping it entirely. For systems relying on fuel or electricity, the failsafe may involve removing the supply. In vehicles, it may trigger collision protection devices like airbags or sirens. For industrial applications, actions include shutting down subsystems such as drilling operations or chemical reactors. Environmental safety measures like triggering fire alarms or sprinklers are also included. The method ensures that the autonomous system responds appropriately to detected issues, enhancing safety and reliability across various applications.
10. The non-transitory computer-readable storage medium of claim 9, wherein the autonomous system is an autonomous vehicle or an autonomous robot.
The invention relates to autonomous systems, specifically autonomous vehicles or robots, and addresses the challenge of improving their operational efficiency and safety. The system includes a computer-readable storage medium containing instructions that, when executed, enable the autonomous system to perform various functions. These functions include receiving sensor data from multiple sensors, processing the data to detect and classify objects in the environment, and generating control signals to navigate the system while avoiding obstacles. The system also incorporates machine learning models to enhance object recognition and decision-making processes. Additionally, the system may include communication modules to exchange data with external systems, such as other autonomous vehicles or infrastructure, to improve coordination and situational awareness. The invention aims to provide a robust and adaptive framework for autonomous systems to operate effectively in dynamic environments, ensuring reliable performance and safety.
11. The non-transitory computer-readable storage medium of claim 9, further comprising writing at least a portion of the dataset to a block of a blockchain.
A system and method for securely storing and managing datasets involves writing at least a portion of the dataset to a block of a blockchain. The blockchain provides a decentralized, tamper-evident ledger to ensure data integrity and immutability. The dataset may include structured or unstructured data, such as transaction records, digital assets, or configuration settings. The system includes a data processing module that prepares the dataset for blockchain storage, which may involve formatting, encrypting, or compressing the data. A blockchain interface module interacts with the blockchain network to create and append new blocks containing the dataset. The system may also include a verification module to validate the integrity of stored data by comparing blockchain records with local copies. This approach enhances security by leveraging blockchain's cryptographic properties, ensuring that once data is recorded, it cannot be altered without detection. The system is particularly useful in applications requiring high levels of trust, such as financial transactions, supply chain tracking, or digital identity management. The blockchain may be public, private, or consortium-based, depending on the security and accessibility requirements of the application.
12. The non-transitory computer-readable storage medium of claim 9, the operations further comprising configuring information for processing by the artificial intelligence or machine learning algorithm, wherein the first data comprises the information configured for processing by the artificial intelligence or machine learning algorithm and sensor data generated by one or more sensors of the autonomous system.
This invention relates to autonomous systems that use artificial intelligence (AI) or machine learning (ML) algorithms to process data. The problem addressed is the efficient integration and processing of diverse data sources, including sensor data and preprocessed information, to improve decision-making in autonomous systems. The invention involves a non-transitory computer-readable storage medium containing instructions that, when executed, perform operations to configure and process data for AI or ML algorithms. The operations include receiving sensor data from one or more sensors of the autonomous system and combining it with preprocessed information that has been specifically formatted for AI or ML processing. This combined data is then used to train or execute the AI or ML algorithm, enabling the autonomous system to make informed decisions based on real-time and preprocessed inputs. The system ensures that the data is properly structured and optimized for the AI or ML model, enhancing accuracy and performance. The invention is particularly useful in applications where autonomous systems must process large volumes of sensor data alongside contextual or preprocessed information to operate effectively.
13. The non-transitory computer-readable storage medium of claim 9, wherein the dataset comprises network data, and wherein the analyzing comprises detecting at least network congestion, network attacks, or both based on the network data.
This invention relates to a computer-implemented method for analyzing network data to detect network congestion, network attacks, or both. The system processes a dataset containing network data, which may include traffic patterns, packet information, or other network-related metrics. The analysis involves identifying anomalies, unusual traffic spikes, or attack signatures within the network data to determine the presence of network congestion or malicious activities such as cyberattacks. The method may also involve generating alerts or reports based on the detected issues, allowing for proactive network management and security measures. The system is designed to enhance network performance and security by providing real-time or near-real-time monitoring and detection capabilities. The analysis may be performed using machine learning, statistical models, or rule-based techniques to accurately identify and classify network issues. The invention aims to improve network reliability and reduce downtime by automating the detection of potential threats and performance bottlenecks.
14. The non-transitory computer-readable storage medium of claim 9, wherein the dataset comprises location data, and wherein the analyzing comprises detecting inconsistencies with respect to distances to one or more obstacles proximate the autonomous system based on the location data and the second data.
This invention relates to autonomous systems and methods for analyzing datasets to detect inconsistencies in location data. The technology addresses the problem of ensuring accurate and reliable navigation by identifying discrepancies between observed location data and expected environmental conditions, particularly in relation to obstacles. The system processes a dataset containing location data, which may include positional information of the autonomous system or its surroundings. The analysis involves comparing this location data with a second set of data, which could include sensor readings, pre-mapped obstacle locations, or other environmental information. By cross-referencing these datasets, the system detects inconsistencies, such as mismatches between the recorded location of the autonomous system and the expected distances to nearby obstacles. This helps identify potential errors in sensor data, mapping inaccuracies, or environmental changes that could affect autonomous navigation. The method may involve real-time or post-processing analysis to flag anomalies, enabling corrective actions like recalibration or route adjustments. The approach improves safety and reliability by ensuring the autonomous system operates within a consistent and predictable environment. The invention is particularly useful in applications like autonomous vehicles, drones, or robotic systems where precise location tracking and obstacle avoidance are critical.
15. The non-transitory computer-readable storage medium of claim 9, wherein the control data comprises instructions to execute a failsafe action, the failsafe action comprising an action selected from the list consisting of: slowing a speed of the autonomous system, increasing a speed of the autonomous system, changing a direction of travel of the autonomous system, stopping the autonomous system, removal of fuel supply, removal of electricity supply, triggering of collision protection devices such as airbags and sirens, turning off of fuel supply/pumps, turning off of reagent supply/pumps, shutting down a drilling subsystem, shutting down one or more chemical reactors, triggering of fire alarms, and triggering of sprinklers.
This invention relates to autonomous systems and their failsafe mechanisms. The technology addresses the need for reliable and diverse failsafe actions to ensure safety and operational integrity when an autonomous system encounters critical errors or hazardous conditions. The system includes a non-transitory computer-readable storage medium containing control data that, when executed, triggers predefined failsafe actions. These actions are designed to mitigate risks and prevent accidents by altering the system's behavior or shutting down critical components. The failsafe actions include slowing or increasing the speed of the autonomous system, changing its direction, or stopping it entirely. Additionally, the system can remove fuel or electricity supply, activate collision protection devices like airbags and sirens, or shut down subsystems such as drilling mechanisms or chemical reactors. For industrial applications, the failsafe actions may also include triggering fire alarms, activating sprinklers, or turning off fuel and reagent pumps. The control data ensures that the autonomous system responds appropriately to detected faults or emergencies, enhancing safety across various operational environments.
17. The system of claim 16, wherein the one or more anomalies correspond to a fault associated with one or more sensors of the autonomous system, a defect in the artificial intelligence or machine learning algorithm, an error associated with the anomaly detection process, or a combination thereof.
The system is designed for monitoring and analyzing autonomous systems, particularly focusing on detecting and diagnosing anomalies that may arise during operation. The system identifies and categorizes anomalies that could stem from various sources, including faults in sensors used by the autonomous system, defects in the artificial intelligence or machine learning algorithms guiding the system, or errors within the anomaly detection process itself. By distinguishing between these different types of anomalies, the system enables more accurate troubleshooting and maintenance, ensuring the reliability and safety of autonomous operations. The system's ability to pinpoint the root cause of anomalies—whether hardware-related, algorithmic, or process-based—helps in reducing downtime and improving system performance. This approach is particularly valuable in autonomous vehicles, robotics, and other automated systems where real-time detection and resolution of issues are critical. The system may also integrate with existing monitoring frameworks to provide a comprehensive view of system health, allowing for proactive maintenance and minimizing operational disruptions.
18. The system of claim 16, wherein the control data comprises instructions to execute a failsafe action, the failsafe action comprising an action selected from the list consisting of: slowing a speed of the autonomous system, increasing a speed of the autonomous system, changing a direction of travel of the autonomous system, stopping the autonomous system, removal of fuel supply, removal of electricity supply, triggering of collision protection devices such as airbags and sirens, turning off of fuel supply/pumps, turning off of reagent supply/pumps, shutting down a drilling subsystem, shutting down one or more chemical reactors, triggering of fire alarms, and triggering of sprinklers.
This invention relates to autonomous systems and methods for controlling such systems in response to detected anomalies or failures. The technology addresses the problem of ensuring safety and operational integrity in autonomous systems when unexpected conditions arise, such as sensor malfunctions, environmental hazards, or system failures. The system monitors the autonomous system's operation and generates control data in response to detected issues. The control data includes instructions to execute predefined failsafe actions to mitigate risks. These actions may include slowing or increasing the system's speed, changing its direction, stopping the system entirely, or cutting off fuel or electricity supply. Additional failsafe actions include triggering collision protection devices like airbags and sirens, shutting down subsystems such as drilling or chemical reactors, and activating fire alarms or sprinklers. The system dynamically adjusts its response based on the nature of the detected anomaly to ensure safe operation. This approach enhances safety by providing automated, real-time interventions to prevent accidents or system damage.
19. The system of claim 16, wherein the one or more processors are configured to write at least a portion of the dataset to a block of the blockchain.
A system for securely storing and managing datasets using blockchain technology addresses the need for tamper-proof data integrity and traceability in distributed environments. The system includes a processor that generates a dataset, such as transaction records, sensor data, or digital documents, and processes this data for blockchain storage. The processor applies cryptographic techniques, such as hashing or digital signatures, to ensure data authenticity and integrity before transmission. The system also includes a network interface for communicating with a blockchain network, where the processed dataset is distributed to multiple nodes for validation and consensus. Once validated, the dataset is recorded in a block of the blockchain, creating an immutable and time-stamped record. The system may further include a user interface for monitoring the status of data transactions and retrieving stored datasets from the blockchain. This approach ensures that data cannot be altered without detection, providing a reliable audit trail for regulatory compliance, supply chain tracking, or financial transactions. The system may also support selective data storage, where only portions of a dataset are written to the blockchain, optimizing storage efficiency while maintaining critical data integrity.
20. The system of claim 19, wherein the one or more processors are configured to synchronize at least the portion of the dataset written to the block of the blockchain with one or more other nodes of the blockchain platform.
A system for managing data in a blockchain platform addresses the challenge of ensuring data consistency and integrity across distributed nodes. The system includes a blockchain platform with multiple nodes, where each node maintains a copy of a blockchain containing blocks of data. The system is configured to write a portion of a dataset to a block of the blockchain, ensuring that the data is cryptographically secured and immutable. The system further synchronizes the written data with other nodes in the blockchain platform, ensuring that all nodes maintain an up-to-date and consistent copy of the blockchain. This synchronization process involves validating the data against consensus rules and propagating the updated block to all participating nodes. The system may also include mechanisms for handling conflicts, such as resolving discrepancies between nodes or re-synchronizing data in case of failures. The synchronization process ensures that the blockchain remains consistent and tamper-proof, providing a reliable and secure distributed ledger for data storage and verification. The system may be applied in various domains, including financial transactions, supply chain tracking, and decentralized applications, where data integrity and consistency are critical.
21. The system of claim 16, wherein the first data comprises information configured for processing by the artificial intelligence or machine learning algorithm and sensor data generated by one or more sensors of the autonomous system.
An autonomous system integrates artificial intelligence (AI) or machine learning (ML) algorithms with sensor data to enhance operational decision-making. The system processes first data, which includes information specifically formatted for AI/ML algorithms and sensor outputs from the autonomous system. This sensor data may originate from various onboard sensors, such as cameras, LiDAR, radar, or other environmental detection devices, providing real-time inputs for the AI/ML models. The processed data enables the system to analyze and interpret its surroundings, make autonomous decisions, and execute tasks without human intervention. The AI/ML algorithms may be trained to recognize patterns, predict outcomes, or optimize performance based on the sensor inputs. This integration allows the autonomous system to adapt dynamically to changing conditions, improving efficiency, safety, and reliability in applications such as autonomous vehicles, robotics, or industrial automation. The system may also incorporate additional data sources or external inputs to further refine its decision-making processes.
22. The system of claim 16, wherein the dataset comprises network data, and wherein the one or more processors are configured to detect at least network congestion, network attacks, or both based on the network data.
This invention relates to a network monitoring and analysis system designed to detect network congestion, network attacks, or both. The system processes network data to identify anomalies, performance issues, or malicious activity within a network infrastructure. The network data may include traffic patterns, packet information, connection logs, or other relevant metrics collected from network devices. The system employs one or more processors to analyze this data, applying algorithms or machine learning techniques to recognize signs of congestion, such as bandwidth saturation or latency spikes, and to detect network attacks, including intrusion attempts, malware propagation, or unauthorized access. The system may also correlate data from multiple sources to improve detection accuracy and reduce false positives. By continuously monitoring and analyzing network behavior, the system helps administrators maintain network security, optimize performance, and respond to threats in real time. The invention builds on a broader system that collects and processes network data, enhancing its capabilities with specialized detection functions for congestion and attack scenarios.
23. The system of claim 16, wherein the dataset comprises location data, and wherein the one or more processors are configured to detect inconsistencies with respect to distances to one or more obstacles proximate the autonomous system based on the location data and the second data.
This invention relates to autonomous systems, specifically improving their ability to detect and resolve inconsistencies in spatial data. The system processes location data from the autonomous system and compares it with additional data (e.g., sensor inputs, maps, or environmental data) to identify discrepancies in distance measurements to nearby obstacles. By analyzing these inconsistencies, the system enhances situational awareness, reducing errors in navigation, obstacle avoidance, and decision-making. The approach helps mitigate risks like false obstacle detections or missed hazards, improving safety and reliability in autonomous operations. The system may integrate multiple data sources, such as GPS, LiDAR, or radar, to cross-validate spatial information and ensure accurate obstacle proximity assessments. This method is particularly useful in dynamic environments where real-time adjustments are critical, such as autonomous vehicles, drones, or robotic systems. The invention addresses challenges in data fusion and error detection, ensuring that autonomous systems maintain precise spatial awareness despite sensor noise or environmental variability.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
August 5, 2020
December 20, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.